def _download_sheet(stock_code, sheet_type, term_type, sheet_part):
detail = 'download finance_sheet(sheet_type[{}], term_type[{}], sheet_part[{}]) failed.'.format(
sheet_type, term_type, sheet_part)
try:
resp = requests.get(_download_url(stock_code, sheet_type, term_type,
sheet_part),
stream=True)
if resp is not None and resp.ok:
lines = [
line.strip() for line in resp.content.decode('gbk').replace(
'\r\n', '\n').strip().split('\n')
]
lines = [
line if line[-1] != ',' else line[0:-1] for line in lines
if line != ''
]
lines.append('')
with codecs.open(
finance_sheet_file_path(stock_code, sheet_type, term_type,
sheet_part), 'w', 'utf-8') as f:
f.write('\n'.join(lines))
else:
raise error.ServerException(error.SERVER_ERR_DOWNLOAD_FAILED,
detail)
except error.ServerException as e:
logger.error('{}.'.format(detail))
raise e
except Exception as e:
raise error.ServerException(
error.SERVER_ERR_DOWNLOAD_FAILED,
'{}.{}'.format(detail, error.exception_string(e)))
def create_directory(directory_path):
if not os.path.exists(directory_path):
os.makedirs(directory_path)
elif os.path.isdir(directory_path):
return
else:
raise error.ServerException('path[{}] exists and is not directory'.format(directory_path))
def clean_directory(directory_path):
if not os.path.exists(directory_path):
os.makedirs(directory_path)
elif os.path.isdir(directory_path):
for path in os.listdir(directory_path):
remove_path(os.path.join(directory_path, path))
else:
raise error.ServerException('path[{}] is not directory'.format(directory_path))
def remove_path(path):
if os.path.exists(path):
if os.path.isdir(path):
shutil.rmtree(path)
elif os.path.isfile(path):
os.remove(path)
else:
raise error.ServerException('nonsupport type for remove path[{}]'.format(path))
else:
return
def download_stock_basics():
utils.clean_directory(BASIC_DIR)
try:
df = ts.get_stock_basics()
utils.df2csv(df, _stock_basics_file_path)
except Exception as e:
logger.error('download_categories failed. {}'.format(
error.exception_string(e)))
utils.clean_directory(BASIC_DIR)
raise error.ServerException(error.SERVER_ERR_DOWNLOAD_FAILED,
error.exception_string(e))
def download_forecast(year, quarter):
try:
df = ts.forecast_data(year, quarter)
df.set_index('code', inplace=True)
utils.df2csv(df, _forecast_file_path(year, quarter))
except Exception as e:
logger.error(
'download_forecast(year[{}], quarter[{}]) failed.{}'.format(
year, quarter, error.exception_string(e)))
raise error.ServerException(error.SERVER_ERR_DOWNLOAD_FAILED,
error.exception_string(e))
def download_categories():
utils.clean_directory(CATEGORY_DIR)
try:
for category_method, (func_name,) in _all_categories.items():
try:
df = getattr(ts, func_name)()
df.set_index('code', inplace=True)
utils.df2csv(df, _category_file_path(category_method))
except Exception as e:
logger.error('download_categories[{}] failed. {}'.format(category_method, error.exception_string(e)))
raise e
except Exception as e:
utils.clean_directory(CATEGORY_DIR)
raise error.ServerException(error.SERVER_ERR_DOWNLOAD_FAILED, error.exception_string(e))
def _get_latest_report_html(report_type, page_no, start_time=None, end_time=None):
to_notice_type = {1: '010305', 2: '010303', 3: '010307', 4: '010301'}
cur_dt = utils.current_datetime()
today = '%d-%02d-%02d' % (cur_dt.year, cur_dt.month, cur_dt.day)
url = 'http://www.cninfo.com.cn/search/search.jsp'
data = {'orderby': 'date11', 'marketType': '', 'stockCode': '', 'keyword': '',
'noticeType': to_notice_type[report_type], 'pageNo': page_no,
'startTime': today if start_time is None else start_time,
'endTime': today if end_time is None else end_time}
resp = requests.post(url, data)
if resp is not None and resp.ok:
return resp.content.decode('gbk')
else:
raise error.ServerException(error.SERVER_ERR_DOWNLOAD_FAILED, 'download html from {} failed'.format(url))
def crawl():
with _crawl_lock:
if CrawlSummary().crawling:
raise error.ServerException(error.SERVER_ERR_OP_CONCURRENT)
else:
CrawlSummary().crawling = True
if CrawlSummary().full_time is None:
CrawlSummary().full_start()
if CrawlSummary().full_complete:
if CrawlSummary().increment_time is None:
CrawlSummary().increment_start()
crawl_increment()
else:
crawl_full()
def finance_sheet_file_path(stock_code, sheet_type, term_type, sheet_part):
# check param
if sheet_type not in sheet_types or term_type not in sheet_types[sheet_type]['terms'] or \
sheet_part not in sheet_types[sheet_type]['parts']:
raise error.ServerException(
error.SERVER_ERR_INTERNAL,
'wrong param: stock_code[{}], sheet_type[{}], term_type[{}], sheet_part[{}]'
.format(stock_code, sheet_type, term_type, sheet_part))
sheet_directory = finance_sheet_directory(stock_code)
if sheet_part == '':
return os.path.join(
sheet_directory, '{}_{}_{}.csv'.format(sheet_type, term_type,
stock_code))
else:
return os.path.join(
sheet_directory, '{}_{}_{}_{}.csv'.format(sheet_type, sheet_part,
term_type, stock_code))
def raise_exception(request, e, content=None):
from jsonrpc.exceptions import ServerError
import traceback
if isinstance(e, error.ServerException):
raise_e = e
else:
raise_e = error.ServerException(error.SERVER_ERR_INTERNAL, '{}\n{}'.format(e, traceback.format_exc()))
err_msg = 'download error code: {}, msg: {}'.format(raise_e.err_code, raise_e.err_msg)
# log err
if content is not None:
logger.error('{} failed. {}'.format(content, err_msg))
# raise exception
if request is not None:
raise ServerError(err_msg)
else:
raise raise_e
def crawler_object(code):
try:
return CrawlerModel.objects.get(code=code)
except ObjectDoesNotExist as e:
raise error.ServerException(error.SERVER_ERR_OBJECT_NOT_EXIST,
error.exception_string(e))
